Loading blueprint versions...
Please wait while we gather all the unique runs for this blueprint.
Please wait while we gather all the unique runs for this blueprint.
Please wait while we prepare the detailed comparison.
Average key point coverage extent for each model across all prompts.
| Prompts vs. Models | Claude Haiku 4 5 | Claude Haiku 4.5 | GPT 5 | GPT OSS 120b | |
|---|---|---|---|---|---|
| Score | 3rd 89.2% | 2nd 90.9% | 1st 91.4% | 4th 79.5% | |
| 100.0% | 100% | 100% | 100% | 100% | |
| 78.4% | 81% | 99% | 86% | 48% | |
| 86.1% | 88% | 94% | 80% | 83% | |
| 80.4% | 78% | 83% | 85% | 76% | |
| 82.0% | 90% | 80% | 90% | 68% | |
| 97.1% | 99% | 97% | 100% | 93% | |
| 85.8% | 82% | 82% | 99% | 82% | |
| 99.0% | 100% | 100% | 98% | 98% | |
| 81.3% | 86% | 85% | 86% | 69% |